No abstract

Human verbal communication includes affective messages which are conveyed through use of emotionally colored words. There has been a lot of research in this direction but the problem of integrating state-of-the-art neural language models with affective information remains an area ripe for exploration. In this paper, we propose an extension to an LSTM (Long Short-Term Memory) language model for generating conversational text, conditioned on affect categories. Our proposed model, Affect-LM enables us to customize the degree of emotional content in generated sentences through an additional design parameter. Perception studies conducted using Amazon Mechanical Turk show that Affect-LM generates naturally looking emotional sentences without sacrificing grammatical correctness. Affect-LM also learns affectdiscriminative word representations, and perplexity experiments show that additional affective information in conversational text can improve language model prediction.

Recent work by Clark et al. (2020) shows that transformers can act as "soft theorem provers" by answering questions over explicitly provided knowledge in natural language. In our work, we take a step closer to emulating formal theorem provers, by proposing PROVER, an interpretable transformer-based model that jointly answers binary questions over rule-bases and generates the corresponding proofs. Our model learns to predict nodes and edges corresponding to proof graphs in an efficient constrained training paradigm. During inference, a valid proof, satisfying a set of global constraints is generated. We conduct experiments on synthetic, hand-authored, and human-paraphrased rule-bases to show promising results for QA and proof generation, with strong generalization performance. First, PROVER generates proofs with an accuracy of 87%, while retaining or improving performance on the QA task, compared to RuleTakers (up to 6% improvement on zero-shot evaluation). Second, when trained on questions requiring lower depths of reasoning, it generalizes significantly better to higher depths (up to 15% improvement). Third, PROVER obtains near perfect QA accuracy of 98% using only 40% of the training data. However, generating proofs for questions requiring higher depths of reasoning becomes challenging, and the accuracy drops to 65% for "depth 5", indicating significant scope for future work. 1

Speech emotion recognition is an important problem with applications as varied as human-computer interfaces and affective computing. Previous approaches to emotion recognition have mostly focused on extraction of carefully engineered features and have trained simple classifiers for the emotion task. There has been limited effort at representation learning for affect recognition, where features are learnt directly from the signal waveform or spectrum. Prior work also does not investigate the effect of transfer learning from affective attributes such as valence and activation to categorical emotions. In this paper, we investigate emotion recognition from spectrogram features extracted from the speech and glottal flow signals; spectrogram encoding is performed by a stacked autoencoder and an RNN (Recurrent Neural Network) is used for classification of four primary emotions. We perform two experiments to improve RNN training : (1) Representation Learning-Model training on the glottal flow signal to investigate the effect of speaker and phonetic invariant features on classification performance (2) Transfer Learning-RNN training on valence and activation, which is adapted to a four emotion classification task. On the USC-IEMOCAP dataset, our proposed approach achieves a performance comparable to the state of the art speech emotion recognition systems.

Age-related macular degeneration (AMD) is an expanding problem as longevity increases worldwide. While inflammation clearly contributes to vision loss in AMD, the mechanism remains controversial. Here we show that neutrophils are important in this inflammatory process. In the retinas of both early AMD patients and in a mouse model with an early AMD-like phenotype, we show neutrophil infiltration. Such infiltration was confirmed experimentally using ribbon-scanning confocal microscopy (RSCM) and IFNλ− activated dye labeled normal neutrophils. With neutrophils lacking lipocalin-2 (LCN-2), infiltration was greatly reduced. Further, increased levels of IFNλ in early AMD trigger neutrophil activation and LCN-2 upregulation. LCN-2 promotes inflammation by modulating integrin β1 levels to stimulate adhesion and transmigration of activated neutrophils into the retina. We show that in the mouse model, inhibiting AKT2 neutralizes IFNλ inflammatory signals, reduces LCN-2-mediated neutrophil infiltration, and reverses early AMD-like phenotype changes. Thus, AKT2 inhibitors may have therapeutic potential in early, dry AMD.